INDEX

Explanations

numerical specifications and measurements related to wattage and power

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abetes

-0.71

первых

-0.68

niająca

-0.63

ymce

-0.63

 سكانية

-0.63

 actionMode

-0.63

__':

-0.62

hala

-0.61

écnicas

-0.61

mergeFrom

-0.60

POSITIVE LOGITS

mm

0.60

 inch

0.51

cc

0.50

"/

0.46

inch

0.45

'/

0.44

0.42

ceğine

0.42

libft

0.42

Activations Density 0.229%

numerical specifications and measurements related to wattage and power

No Comments

No Known Activations